Closed-ended Task T-2 on DanmakuTPP-QA
1.11RMSELlama-3.3-70B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-3.3-70B-InstructModel Category=LLMs2026.02 | 1.11 | |
| Qwen2.5-VL-72BModel Category=MLLMs2026.02 | 1.14 | |
| Qwen2.5-VL-32BModel Category=MLLMs2026.02 | 1.26 | |
| Qwen2.5-72B-InstructModel Category=LLMs2026.02 | 1.28 | |
| DeepSeek-V3Model Category=LLMs2026.02 | 1.3 | |
| Qwen3-30B-A3BModel Category=LLMs2026.02 | 1.33 | |
| Gemma3-27BModel Category=MLLMs2026.02 | 1.33 | |
| Qwen2.5-VL-3BModel Category=Finetuned2026.02 | 1.35 | |
| Qwen3-235B-A22BModel Category=LLMs2026.02 | 1.39 | |
| MM-TPPModel Category=Finetuned2026.02 | 1.49 | |
| Qwen2.5-32B-InstructModel Category=LLMs2026.02 | 1.52 | |
| Qwen3-8BModel Category=LLMs2026.02 | 1.8 | |
| Qwen2.5-VL-7BModel Category=MLLMs2026.02 | 11.61 | |
| Qwen2.5-7B-InstructModel Category=LLMs2026.02 | 27.64 |